根据蓝印花布纹样的风格特征,文章提出一种端到端的蓝印花布纹样自动生成方法,实现简笔画图像向蓝印花布单纹样的自动迁移。针对蓝印花布的抽象风格和小数据集问题,重新构造CycleGAN生成网络中的编码器和解码器,使用SE(squeeze and exci...根据蓝印花布纹样的风格特征,文章提出一种端到端的蓝印花布纹样自动生成方法,实现简笔画图像向蓝印花布单纹样的自动迁移。针对蓝印花布的抽象风格和小数据集问题,重新构造CycleGAN生成网络中的编码器和解码器,使用SE(squeeze and excitation)注意力模块和残差模块与原始的卷积模块串联,提高特征提取能力和网络学习能力。同时减少生成网络中转换器的残差块层数,降低过拟合。实验结果表明,基于SE注意力CycleGAN网络方法自动生成的蓝印花布新纹样主观性上更贴合原始风格,与原图更加接近,有助于蓝印花布的数字化传承和创新。展开更多
This study proposes an architecture for the prediction of extremist human behaviour from projected suicide bombings.By linking‘dots’of police data comprising scattered information of people,groups,logistics,location...This study proposes an architecture for the prediction of extremist human behaviour from projected suicide bombings.By linking‘dots’of police data comprising scattered information of people,groups,logistics,locations,communication,and spatiotemporal characters on different social media groups,the proposed architecture will spawn beneficial information.This useful information will,in turn,help the police both in predicting potential terrorist events and in investigating previous events.Furthermore,this architecture will aid in the identification of criminals and their associates and handlers.Terrorism is psychological warfare,which,in the broadest sense,can be defined as the utilisation of deliberate violence for economic,political or religious purposes.In this study,a supervised learning-based approach was adopted to develop the proposed architecture.The dataset was prepared from the suicide bomb blast data of Pakistan obtained from the South Asia Terrorism Portal(SATP).As the proposed architecture was simulated,the supervised learning-based classifiers na飗e Bayes and Hoeffding Tree reached 72.17%accuracy.One of the additional benefits this study offers is the ability to predict the target audience of potential suicide bomb blasts,which may be used to eliminate future threats or,at least,minimise the number of casualties and other property losses.展开更多
The increased production and price of rare earth elements(REEs) are indicative of their importance and of growing global attention. More accurate and practical exploration procedures are needed for REEs, and for other...The increased production and price of rare earth elements(REEs) are indicative of their importance and of growing global attention. More accurate and practical exploration procedures are needed for REEs, and for other geochemical resources. One such procedure is a multivariate approach. In this study, five classifiers, including multilayer perceptron(MLP), Bayesian, k-Nearest Neighbors(KNN), Parzen, and support vector machine(SVM),were applied in supervised pattern classification of bulk geochemical samples based on REEs, P, and Fe in the Kiruna type magnetite-apatite deposit of Se-Chahun,Central Iran. This deposit is composed of four rock types:(1) High anomaly(phosphorus iron ore),(2) Low anomaly(metasomatized tuff),(3) Low anomaly(iron ore), and(4)Background(iron ore and others). The proposed methods help to predict the proper classes for new samples from the study area without the need for costly and time-consuming additional studies. In addition, this paper provides a performance comparison of the five models. Results show that all five classifiers have appropriate and acceptable performance. Therefore, pattern classification can be used for evaluation of REE distribution. However, MLP and KNN classifiers show the same results and have the highest CCRs in comparison to Bayesian, Parzen, and SVM classifiers. MLP is more generalizable than KNN and seems to be an applicable approach for classification and predictionof the classes. We hope the predictability of the proposed methods will encourage geochemists to expand the use of numerical models in future work.展开更多
In many machine learning problems, a large amount of data is available but only a few of them can be labeled easily. This provides a research branch to effectively combine unlabeled and labeled data to infer the label...In many machine learning problems, a large amount of data is available but only a few of them can be labeled easily. This provides a research branch to effectively combine unlabeled and labeled data to infer the labels of unlabeled ones, that is, to develop transductive learning. In this article, based on Pattern classification via single sphere （SSPC）, which seeks a hypersphere to separate data with the maximum separation ratio, a progressive transductive pattern classification method via single sphere （PTSSPC） is proposed to construct the classifier using both the labeled and unlabeled data. PTSSPC utilize the additional information of the unlabeled samples and obtain better classification performance than SSPC when insufficient labeled data information is available. Experiment results show the algorithm can yields better performance.展开更多
文摘根据蓝印花布纹样的风格特征,文章提出一种端到端的蓝印花布纹样自动生成方法,实现简笔画图像向蓝印花布单纹样的自动迁移。针对蓝印花布的抽象风格和小数据集问题,重新构造CycleGAN生成网络中的编码器和解码器,使用SE(squeeze and excitation)注意力模块和残差模块与原始的卷积模块串联,提高特征提取能力和网络学习能力。同时减少生成网络中转换器的残差块层数,降低过拟合。实验结果表明,基于SE注意力CycleGAN网络方法自动生成的蓝印花布新纹样主观性上更贴合原始风格,与原图更加接近,有助于蓝印花布的数字化传承和创新。
文摘This study proposes an architecture for the prediction of extremist human behaviour from projected suicide bombings.By linking‘dots’of police data comprising scattered information of people,groups,logistics,locations,communication,and spatiotemporal characters on different social media groups,the proposed architecture will spawn beneficial information.This useful information will,in turn,help the police both in predicting potential terrorist events and in investigating previous events.Furthermore,this architecture will aid in the identification of criminals and their associates and handlers.Terrorism is psychological warfare,which,in the broadest sense,can be defined as the utilisation of deliberate violence for economic,political or religious purposes.In this study,a supervised learning-based approach was adopted to develop the proposed architecture.The dataset was prepared from the suicide bomb blast data of Pakistan obtained from the South Asia Terrorism Portal(SATP).As the proposed architecture was simulated,the supervised learning-based classifiers na飗e Bayes and Hoeffding Tree reached 72.17%accuracy.One of the additional benefits this study offers is the ability to predict the target audience of potential suicide bomb blasts,which may be used to eliminate future threats or,at least,minimise the number of casualties and other property losses.
文摘The increased production and price of rare earth elements(REEs) are indicative of their importance and of growing global attention. More accurate and practical exploration procedures are needed for REEs, and for other geochemical resources. One such procedure is a multivariate approach. In this study, five classifiers, including multilayer perceptron(MLP), Bayesian, k-Nearest Neighbors(KNN), Parzen, and support vector machine(SVM),were applied in supervised pattern classification of bulk geochemical samples based on REEs, P, and Fe in the Kiruna type magnetite-apatite deposit of Se-Chahun,Central Iran. This deposit is composed of four rock types:(1) High anomaly(phosphorus iron ore),(2) Low anomaly(metasomatized tuff),(3) Low anomaly(iron ore), and(4)Background(iron ore and others). The proposed methods help to predict the proper classes for new samples from the study area without the need for costly and time-consuming additional studies. In addition, this paper provides a performance comparison of the five models. Results show that all five classifiers have appropriate and acceptable performance. Therefore, pattern classification can be used for evaluation of REE distribution. However, MLP and KNN classifiers show the same results and have the highest CCRs in comparison to Bayesian, Parzen, and SVM classifiers. MLP is more generalizable than KNN and seems to be an applicable approach for classification and predictionof the classes. We hope the predictability of the proposed methods will encourage geochemists to expand the use of numerical models in future work.
基金supported by the National Natural Science of China(6057407560705004).
文摘In many machine learning problems, a large amount of data is available but only a few of them can be labeled easily. This provides a research branch to effectively combine unlabeled and labeled data to infer the labels of unlabeled ones, that is, to develop transductive learning. In this article, based on Pattern classification via single sphere （SSPC）, which seeks a hypersphere to separate data with the maximum separation ratio, a progressive transductive pattern classification method via single sphere （PTSSPC） is proposed to construct the classifier using both the labeled and unlabeled data. PTSSPC utilize the additional information of the unlabeled samples and obtain better classification performance than SSPC when insufficient labeled data information is available. Experiment results show the algorithm can yields better performance.
